基于Zernike矩的区域匹配方法

在基于区域的立体匹配中,由于遮掩、区域变形及光照条件会对匹配算法造成很大的影响,而传统的顺序性约束、唯一性约束、外极线约束和邻域约束并不能很好地解决这些问题,而近几年提出的相对位置约束虽能解决其中大部分问题,但对于区域的遮掩情况依然效果不佳。为此提出了一种新的基于Zernike矩的区域匹配算法,该算法在相对位置约束的基础上,采用中心距离和Zernike矩构造了新的费用函数,并提出根据匹配区域之间中心距离的大小来动态评判费用函数的权重系数值,从而提高了算法的性能。实验结果表明,该算法优于原方法,且对于区域的遮掩和变形情况都具备更好的识别性能,是一种行之有效的区域匹配算法。     

结合Ostu阈值法的最小生成树图像分割算法

基于最小生成树的图像分割算法是一种全局最优的算法，然而会出现图像细节的处理不甚理想的问题，即分割结果出现不同程度的过分割和欠分割的现象。针对这一现象，根据图像全局和区域间的最大类间方差（Ostu），将Ostu阈值法与最小生成树（MST）算法相结合，提出了一种基于MST的Ostu阈值法图像分割准则。该图像分割算法是一种MST的优化方法，将区域合并判决条件取决于相互合并的两个区域的Ostu阈值，又考虑到较小的区域包含在较大的目标区域中或者背景区域中，再次使用Ostu阈值进行区域合并。该方法通过实验证明，可以有效地减弱图像的过分割与欠分割比例，减少了误分割率。     

一种基于区域特征关联的图像语义标注方法

图像语义的标注需要解决图像高层语义和底层特征间存在的语义鸿沟。采用基于图像分割、并结合图像区域特征抽取的方法,建立图像区域语义与底层特征间的关联,采用基于距离的分类算法,计算区域特征间的相似性,并对具有相同或相近特征的区域的语义采用关联关键字的方法进行区分,用关键字实现图像语义的自动标注。     

基于聚类的自动颜色传输

提出了一种基于聚类的颜色传输算法。利用算法可以自动完成彩色图像间、彩色图像和黑白图像间的全局或者局部颜色传输。首先,对于源图像,将采用混合高斯模型进行建模,并利用EM算法求得相应参数完成图像自动聚类。对于目标图像,如果是彩色图像,采用同样聚类方法。如果是黑白图像,采用K-Means聚类法。完成源图像和目标图像的聚类,并建立双方聚类区域的对应关系后,通过改变目标图像中像素的Lαβ通道值完成色彩传输功能。实验证明,算法高效且无需人工干预,颜色传输效果很理想。     

Example‐based Multiple Local Color Transfer by Strokes

This paper investigates a new approach for color transfer. Rather than transferring color from one image to another globally, we propose a system with a stroke‐based user interface to provide a direct indication mechanism. We further present a multiple local color transfer method. Through our system the user can easily enhance a defect (source) photo by referring to some other good quality (target) images by simply drawing some strokes. Then, the system will perform the multiple local color transfer automatically. The system consists of two major steps. First, the user draws some strokes on the source and target images to indicate corresponding regions and also the regions he or she wants to preserve. The regions to be preserved which will be masked out based on an improved graph cuts algorithm. Second, a multiple local color transfer method is presented to transfer the color from the target image(s) to the source image through gradient‐guided pixel‐wise color transfer functions. Finally, the defect (source) image can be enhanced seamlessly by multiple local color transfer based on some good quality (target) examples through an interactive and intuitive stroke‐based user interface.     

Boundary finding based multi-focus image fusion through multi-scale morphological focus-measure

Multi-focus image fusion aims to extract the focused regions from multiple partially focused images of the same scene and then combine them together to produce a completely focused image. Detecting the focused regions from multiple images is key for multi-focus image fusion. In this paper, we propose a novel boundary finding based multi-focus image fusion algorithm, in which the task of detecting the focused regions is treated as finding the boundaries between the focused and defocused regions from the source images. According to the found boundaries, the source images could be naturally separated into regions with the same focus conditions, i.e., each region is fully focused or defocused. Then, the focused regions can be found out by selecting the regions with greater focus-measures from each pair of regions. To improve the precision of boundary detection and focused region detection, we also present a multi-scale morphological focus-measure, effectiveness of which has been verified by using some quantitative evaluations. Different from the general multi-focus image fusion algorithms, our algorithm fuses the boundary regions and non-boundary regions of the source images respectively, which helps produce a fusion image with good visual quality. Moreover, the experimental results validate that the proposed algorithm outperforms some state-of-the-art image fusion algorithms in both qualitative and quantitative evaluations.     

基于区域协方差的图像超像素生成

图像分割是指将图像分割成一些互不重叠的区域,各区域内部具有相同或相近的某些特定属性,而不同区域之间的属性则相差明显。在图像处理的许多应用中,由于像素级处理的方法因图像数据量庞大、运算规模较大而需要耗费大量的运行时间,因此对图像进行超像素分割预处理是很有必要的一个步骤。基于区域协方差分析,提出了一种新的像素块相似度度量方法;基于像素块相似度度量提出了一种图像超像素生成的鲁棒方法。该方法首先利用K-means算法对输入图像 进行初始聚类分割成若干小区域,对每个小区域利用区域协方差矩阵描述其特征信息;然后利用小区域块之间的区域协方差距离来构造相似度矩阵,结合Graph-based与K-means方法对区域块聚类生成图像超像素。与其它方法相比,该方法在生成较紧凑超像素的同时能更好地保持图像边缘特征信息,改善了图像欠分割错误,减少了不必要的过分割现象。将图像超像素生成方法应用于图像风格化中可以快速生成油画风格的风格化图像。     

小波变换在三维医学图象分割中的应用

本文将多尺度小波变换应用到三维医学图象分割中的阈值选取中．由于小波变换在较大尺度，由噪音引起的细小突变较少，可描述信号的整体行为，取较大尺度的由负到正的零交叉点来确定图象的阈值，再逐步到相邻的小尺度由粗到精地确定精确的阈值．用以上算法对三维医学图象进行二值化后，根据待提取组织或区域的特征，再选取合适的数学形态学操作，最后对区域进行种子填充．从实验结果可以看出分割效果较好，能够满足三维重建的要求．     

A New Text Location Approach Based Wavelet

With the advancement of content-based retrieval technology, the importance of semantics for text information contained in images attracts many researchers. An algorithm which will automatically locate the textual regions in the input image will facilitate     

基于空间重叠度的DTBSVM多类分类算法

针对传统的DTBSVM算法中判断类间的可分的难易程度时可能造成的错误判断,提出了基于空间重叠度的DTSVM多类分类方法。该方法通过计算已知的类别样本在空间中的重叠度,合并有重叠的类,组合为一个新的类,再基于一种有效的类间可分性准则进行划分,使得容易划分的类能从决策树的根节点开始逐层分割出来,再划分有类间重叠的类,这样就可以尽量地避免“误差累积”的风险,构造出分类效果好的决策树结构。实验结果表明,该方法大大提升了DTSVM多类分类算法的分类正确率。